Model comparison
GPT-4 vs Mercury 2
Mercury 2 is the stronger model overall, scoring 39.1 to 29.1 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Mercury 2 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mercury 2 leads 53.8 to 34.9.
- The biggest single-benchmark swing is WeirdML: 12.4% for GPT-4 and 43.2% for Mercury 2.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $30 / $60 for GPT-4.
- Mercury 2 accepts more context: 128K tokens versus 8K.
Side by side
| GPT-4 | Mercury 2 | |
|---|---|---|
| Provider | OpenAI | Inception |
| Noometry Index | 29.1 | 39.1 |
| Released | 2023-03-14 | 2026-02-20 |
| Weights | Proprietary | Proprietary |
| Context window | 8K | 128K |
| Max output | 8K | 50K |
| Input $ / M tokens | $30 | $0.25 |
| Output $ / M tokens | $60 | $0.75 |
| Results tracked | 38 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury 2 leads
GPT-4: 31.6 (#283), Mercury 2: 33.5 (#255)
| Benchmark | GPT-4 | Mercury 2 |
|---|---|---|
| WeirdML | 12.4% | 43.2% |
| LMArena Coding | 1254 | 1391 |
| LMArena WebDev | — | 1171 |
| SciCode | — | 38.7% |
| BigCodeBench Instruct | 46% | — |
| BigCodeBench Complete | 57.2% | — |
| ALE-Bench | — | 785.58 |
| HumanEval+ | 79.3% | — |
Agentic & Tool Use Not comparable
GPT-4: —, Mercury 2: —
| Benchmark | GPT-4 | Mercury 2 |
|---|---|---|
| METR Time Horizons | 36.1% | — |
Reasoning Mercury 2 leads
GPT-4: 17.8 (#289), Mercury 2: 23.8 (#170)
| Benchmark | GPT-4 | Mercury 2 |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1362 |
| CritPt | — | 0.8% |
| Chess Puzzles | 4% | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 62.7% | — |
| LMCA | 17.1% | — |
| BIG-Bench Hard | 75.1% | — |
| Epoch Capabilities Index | 125.89 | — |
| ForecastBench | 57.8 | — |
| HellaSwag | 95.3% | — |
| WinoGrande | 87.5% | — |
Math Not comparable
GPT-4: 10.8 (#309), Mercury 2: —
| Benchmark | GPT-4 | Mercury 2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| LMArena Math | 1269 | — |
| MATH Level 5 | 23% | — |
| GSM8K | 92% | — |
Knowledge Mercury 2 leads
GPT-4: 18.4 (#282), Mercury 2: 36.2 (#172)
| Benchmark | GPT-4 | Mercury 2 |
|---|---|---|
| LMArena Expert | 1211 | 1358 |
| GPQA Diamond | 35.7% | — |
| Vectara Hallucination Rate | — | 12.3% |
| MMLU | 86.4% | — |
| TriviaQA | 84.8% | — |
Multilingual Mercury 2 leads
GPT-4: 40.6 (#215), Mercury 2: 46.6 (#157)
| Benchmark | GPT-4 | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1246 | 1331 |
| LMArena Chinese | 1242 | 1417 |
| LMArena Russian | 1251 | 1304 |
| LMArena French | 1283 | — |
| LMArena German | 1251 | — |
| LMArena Japanese | 1209 | — |
| LMArena Korean | 1184 | — |
| LMArena Spanish | 1261 | — |
Instruction Following Mercury 2 leads
GPT-4: 65.3 (#222), Mercury 2: 70.2 (#165)
| Benchmark | GPT-4 | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1241 | 1329 |
Long Context Mercury 2 leads
GPT-4: 37.7 (#212), Mercury 2: 40.5 (#154)
| Benchmark | GPT-4 | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1244 | 1330 |
Writing & Preference Mercury 2 leads
GPT-4: 34.9 (#268), Mercury 2: 53.8 (#155)
| Benchmark | GPT-4 | Mercury 2 |
|---|---|---|
| LMArena Text | 1263 | 1355 |
| LMArena Creative Writing | 1244 | 1289 |
| LMArena Multi-Turn | 1257 | 1358 |
| EQ-Bench Creative Writing | 752 | — |
Frequently asked questions
Is GPT-4 better than Mercury 2?
Mercury 2 is the stronger model overall, scoring 39.1 to 29.1 on the Noometry Index.
Which is cheaper, GPT-4 or Mercury 2?
Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; GPT-4 lists at $30 and $60.
Is GPT-4 or Mercury 2 better for coding?
Mercury 2 scores higher on coding benchmarks: 33.5 versus 31.6 in the Noometry coding category.
Which has the bigger context window?
Mercury 2 does, with 128K tokens against 8K.
How many benchmarks do GPT-4 and Mercury 2 share?
12 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Mercury 2 has 17.